Back to jobs

Senior AI Agent Engineer

Pay
Pay not listed
Work setting
Remote — work setting source
Work setup in the employer’s posting: TELECOMMUTE
From the employer’s posting
Employment
Not stated
Apply at EPAM Systems

Posting record

Report an error
Status in our records
Live
First seen by us
Nov 1, 202620 days ago
Recorded sightings
21
Last seen by us
Nov 21, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Time since we first saw it

Day 20

Up longer than most. Similar jobs usually come down between day 1 and day 15.

From 1,376 similar postings that came down. Coming down is not always a hire.

EPAM Systems is hiring

892 open jobs

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • Azure
Where the posting names them
Personally build working prototypes and production-grade slices of the solution, from design through implementation, testing, and deployment Develop agent workflows and production deployments using cloud managed services for AI hosting (e.g., Bedrock, Azure AI Foundry, Vertex AI), selecting services and development tools against the system's requirements Implement and operate an LLM gateway & routing layer covering model tiering, quota/cost control, and observability (e.g., LiteLLM, APIM AI Gateway) Design memory and context-management approaches for multi-step workflows, including state persistence, retrieval quality, retention, and isolation between users or engagements Build and maintain MCP servers and tool integrations for authorized security workflows, including reconnaissance, scanners, controlled exploit tooling, and internal services.
You can independently learn an unfamiliar language or runtime and validate your implementation through tests and diagnostics Depth in at least one technical area and the ability to evaluate language, runtime, and framework trade-offs against the system's requirements, including concurrency, performance, maintainability, and integration needs Experience designing systems or substantial components, evaluating alternatives, and independently making technical decisions within an agreed scope Practical experience with MCP, tool use, prompt and context engineering, memory, and agent evaluation, including testing behavior across multiple steps and failure conditions Practical experience with cloud managed services for AI hosting (e.g., Bedrock, Azure AI Foundry, Vertex AI), including runtime, state, identity, integration, and observability concerns, and the ability to adopt an unfamiliar platform through working implementations Production engineering skills in API design, asynchronous processing, persistence, authentication and authorization, observability, retries, and security boundaries.

Your next step

Complete your application on careers.epam.com. The employer’s form will show what is required.

Already applied? Track this application

Job description

View original posting ↗

Design and deliver AI agent systems that remain reliable beyond a successful demonstration. In this role, you will own technical decisions and delivery for a defined system or substantial component, from requirements and design through production operation. You will combine strong software engineering with practical agent development, make trade-offs explicit, and help other engineers deliver high-quality work. We welcome engineers from different programming backgrounds. We value depth in your existing language and the ability to learn the languages and tools needed for the role. Responsibilities Design, build, deploy, and operate agent systems across execution, memory, identity, tool integration, and observability within your area of responsibility Work directly with customers and stakeholders to turn needs into functional requirements and measurable acceptance criteria. Personally build working prototypes and production-grade slices of the solution, from design through implementation, testing, and deployment Develop agent workflows and production deployments using cloud managed services for AI hosting (e.g., Bedrock, Azure AI Foundry, Vertex AI), selecting services and development tools against the system's requirements Implement and operate an LLM gateway & routing layer covering model tiering, quota/cost control, and observability (e.g., LiteLLM, APIM AI Gateway) Design memory and context-management approaches for multi-step workflows, including state persistence, retrieval quality, retention, and isolation between users or engagements Build and maintain MCP servers and tool integrations for authorized security workflows, including reconnaissance, scanners, controlled exploit tooling, and internal services. Define contracts, permissions, approval boundaries, and recovery behavior Establish automated tests and agent evaluations for your components. Distinguish model-quality issues from software defects, and cover tool failures, interrupted execution, and unintended repeated actions Diagnose production issues using logs, metrics, and traces. Improve reliability, latency, and cost, and verify that mitigation and recovery work as intended Contribute to CI/CD, release checks, rollback plans, code review, and technical documentation. Mentor less experienced engineers and communicate decisions clearly to technical and non-technical stakeholders Requirements Substantial production software engineering experience, typically five or more years, including at least one year delivering LLM-based agents to production. You can explain your contribution, the trade-offs you made, and the operational results Strong programming skills and production experience in at least one general-purpose language, together with hands-on agent development using SDKs, frameworks, or direct model APIs. You can independently learn an unfamiliar language or runtime and validate your implementation through tests and diagnostics Depth in at least one technical area and the ability to evaluate language, runtime, and framework trade-offs against the system's requirements, including concurrency, performance, maintainability, and integration needs Experience designing systems or substantial components, evaluating alternatives, and independently making technical decisions within an agreed scope Practical experience with MCP, tool use, prompt and context engineering, memory, and agent evaluation, including testing behavior across multiple steps and failure conditions Practical experience with cloud managed services for AI hosting (e.g., Bedrock, Azure AI Foundry, Vertex AI), including runtime, state, identity, integration, and observability concerns, and the ability to adopt an unfamiliar platform through working implementations Production engineering skills in API design, asynchronous processing, persistence, authentication and authorization, observability, retries, and security boundaries. You can investigate issues that span multiple components Experience with automated testing, CI/CD, code review, and AI-assisted development, together with a disciplined approach to validating generated output. You can clarify requirements, communicate designs, and support the growth of other engineers Proficiency in English at a B2+ level Nice to have Experience in application security, web penetration testing, or red-teaming within an authorized scope Experience with sandboxed code execution, browser agents, or autonomous tool orchestration Experience improving evaluation coverage, deployment safety, or operating costs for agent systems Experience conducting technical interviews or contributing to engineering standards and knowledge sharing

About EPAM Systems

People
About 3,012 in 2024.Benefit plan filings (Form 5500)
Company
Listed as EPAM.
H-1B visas
21 approved for new hires in fiscal 2025.US Citizenship and Immigration Services

Demand for AI Engineer roles

New AI Engineer postings at the employers we follow are up 340% over the last 6 weeks compared with the 6 before.

Weekly new AI Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 78, the most 803, and the latest week had 438.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under AI Engineer, by the work the posting describes.

AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.

Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.

An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

Location not supplied.

Working pattern and location restrictions need checking in the full posting.

Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.