Summary
✨ AI‑Generated
A highly hands-on engineering role building and shipping AI-native systems end to end. You’ll develop agents, workflows, retrieval systems, evaluation pipelines, and observability, while engineering for failure with retries, model fallbacks, cost controls, and human oversight. The role combines production coding with close engagement with experts and end users.
Highlights
Builder-focused role developing AI-native systems end to end, including agents, workflows, RAG, evaluations, and observability. Strong emphasis on production quality, reliability, cost controls, human oversight, and close collaboration with domain experts and end users.
Description
We are building AI-native solutions for our clients — products where LLM and its harness are the core of the value.
This is a builder's role: you and your team are responsible for building agentic systems, writing the production code, and standing up the evals and observability.
You will work closely with SMEs and end-users to understand where the real value lies, and you design the feedback loops.
Responsibilities
Design, build and ship AI-native systems E2E — agents, workflows, RAG and the harness: custom tool calling, sandboxing, context engineering and sub-agents, caching, compactionBuild the evaluation pipelines and use them to prove the system is genuinely usefulDesign for failure in the agent loop: retries, model fallbacks, cost limits and human-in-the-loop on consequential actionsCapture domain expertise and repeatable workflows so what works on one engagement carries to the nextEngage early to help shape the use case and check technical feasibilityWrite production-grade Python: integrations, APIs, data access, deploymentWork directly with SMEs and end-users through interviews, UAT and observing the real workflow, and validate that the system fits how people actually work
Requirements
7+ years of engineering experience, with a strong recent track record building production AI / LLM applications (not prototypes or research only)Strong agent-design judgment — task-harness fit, matching the harness to the context, failures and policies of the actual task rather than calling a model in a loopCapability to operate close to the client: lead discovery and feasibility conversations, work directly with SMEs and end-users, and explain technical trade-offs to both technical and non-technical audiencesHands-on experience with agentic frameworks (LangChain, LangGraph, Semantic Kernel) and major LLM providers (OpenAI, Anthropic, Google Gemini)Expert-level Python and solid software engineering fundamentalsStrong RAG and retrieval skills: vector databases, embeddings, hybrid search, re-ranking, chunking and context managementProven experience evaluating generative AI quality — LLM-based evaluation, heuristics, custom eval frameworks — and using observability/tracing tools (LangSmith, Arize Phoenix, Langfuse)Production deployment experience on at least one major cloud (AWS, Azure, GCP) with containerization, CI/CDSound judgment under ambiguity — scoping, sequencing and making the call on speed vs.
quality vs.
scopeEnglish at C1 level
Nice to have
Experience designing experiments, A/B testing and iterating on AI products against real user behavior and business metricsBackground in NLP, Data Science or applied ML, with experience moving models into productionFamiliarity with MCP, A2A and Agent Skills, and emerging agent standardsExperience with enterprise AI platforms (AWS Bedrock AgentCore, Databricks Genie, Microsoft Foundry)Exposure to AI governance, security and compliance (guardrails, prompt-injection prevention)
We offer
We connect like-minded people:Delivering innovative solutions to industry leaders, making a global impactEnjoyable working environment, whether it is the vibrant office or the comfort of your own homeOpportunity to work abroad for up to two months per yearRelocation opportunities within our offices in 55+ countriesCorporate and social eventsWe invest in your growth:Leadership development, career advising, soft skills and well-being programsCertifications, including GCP, Azure and AWSUnlimited access to EPAM's internal learning databaseFree English classes with certified teachersWe cover it all:Monetary bonuses for engaging in the referral programMedical & family care packageSix trust days per year (sick leave without a medical certificate)Coverage of psychology sessions of your choiceDiscounts for fitness clubs and sports programsBenefits package (sports activities, a variety of stores and services)
EPAM is global leader in AI transformation engineering and integrated consulting, serving Forbes Global 2000 companies and ambitious startups.
With over thirty years of expertise in custom software, product and platform engineering, we empower our clients to become AI-Native enterprises, driving measurable value from innovation and digital investments.
Experience the freedom of remote work from anywhere in Kyrgyzstan, whether it's the comfort of your home or our modern office in Bishkek.
