Senior AI Engineer

We are seeking a hands-on Senior AI Engineer who designs, builds, and operates production GenAI systems – agentic workflows, RAG pipelines, and LLM-backed services with real users and real SLAs. This is an engineering role, not a research role. The bar is reliability, latency, cost, observability, and safe deployment at scale, with end-to-end ownership from architecture through on-call. Typical workloads include enterprise knowledge platforms, conversational analytics, agentic automation, and LLM-augmented data products. Unlock the potential of remote work in Kazakhstan, giving you the flexibility to work from home or access our offices in Astana, Almaty or Karaganda. Responsibilities Design agent orchestration (graph/state, conditional routing, tool calling, memory, checkpointing) in LangGraph / LangChain or equivalentBuild production RAG end-to-end: chunking, embeddings, vector stores, hybrid retrieval, reranking, caching, and grounded synthesisOwn Python / FastAPI services – async, SSE streaming, session handling, and structured error contractsInstrument with tracing and evaluation harnesses (MLflow, OpenTelemetry, or equivalent) for accuracy, cost, and regressionShip on Docker + Kubernetes (EKS/AKS/GKE) via CI/CD with test, eval, and canary gatesDrive LLM cost engineering – model routing, prompt optimization, caching, token accounting, and build-vs-buy decisionsApply GenAI safety & governance: hallucination control, prompt-injection defense, PII handling, and HITL where requiredPartner with data engineering on semantic layers and pipelines (PySpark / SQL where applicable) Requirements 5+ years in software engineering, with 2+ years shipping production LLM / agentic systems (not POCs or research)Proficiency in Python and FastAPI (async, REST, SSE)Production expertise in LangChain and LangGraph (or equivalent serious production experience with LlamaIndex, AutoGen, or MCP stacks)Background in production RAG: embeddings, chunking, and hybrid retrieval with reranking and cachingSkills in vector databases such as Pinecone, Weaviate, pgvector, OpenSearch, or Databricks Vector SearchKnowledge of at least one major LLM provider in production – AWS Bedrock (preferred), OpenAI / Azure OpenAI, or Anthropic – with model selection and routing trade-offsCompetency in Kubernetes and Docker in real production environments (EKS/AKS/GKE)Expertise in cloud engineering on AWSFamiliarity with observability and tracing tools (MLflow, LangSmith, OpenTelemetry), evaluation harnesses, and latency/cost ownershipCapability to build CI/CD for AI systems (GitHub Actions, Jenkins, or equivalent) with test/eval gatesStrong written and spoken English (B2 level); able to own design discussions with engineering and business stakeholders independently Nice to have Databricks depth – MLflow (tracking & serving), Vector Search, Unity Catalog / Metric Views, PySpark / SQLExperience with LLM fine-tuning – PEFT, LoRA, QLoRAUnderstanding of MCP servers and tool integrationQualifications in GenAI governance & FinOps – auditability, prompt-injection hardening, PII, and token cost in regulated environmentsBackground in classical ML / DL – NLP, BERT-family, time-series, and CV 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 teachersDiscounts in local language schools, including online courses for the Kazakh languageWe cover it all:Participation in the Employee Stock Purchase PlanMonetary 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 choiceBenefits package (sports activities, a variety of stores and services)Housing support program: preferential mortgage access via Otbasy Bank partnership 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.