Senior AI Engineer with RAG and Agentic architectures

EPAM Systems; Turkey; On-site; TRY 5,900,000 - 8,850,000; Full time

Benefits offered by this job

Private health insurance

Continuous upskilling

Internal courses access

Career development programs

Job summary

EPAM Systems, Inc. is seeking a Senior AI Engineer to design and deliver LLM-powered applications and agentic systems that solve real user problems. You will span the full applied-AI stack from RAG pipelines to multi-step agents that reason and automate workflows.

Collaborate with product and data teams to productionize AI features, optimize performance and cost, and implement safety guardrails. Strong Python, LLM APIs, and vector database experience are required.

Qualifications

• 3+ years in software or ML engineering, including hands-on experience building and shipping applications with LLMs.
• Proven experience delivering applied-AI systems end to end.
• Advanced proficiency in Python.
• Hands-on background in building RAG systems — embeddings, retrieval, and reranking with vector databases.

Responsibilities

• Design and deliver production LLM applications — chat, copilots, assistants, and autonomous workflows — from concept to scale.
• Build and implement RAG pipelines: chunking, embeddings, vector search, reranking, and grounding to reduce hallucination and improve relevance.
• Develop agentic architectures: multi-step reasoning, tool/function calling, planning, memory, and multi-agent orchestration.
• Contribute to automation of business and engineering workflows using agentic AI and workflow automation tooling.
• Define prompt and context strategies; build evaluation harnesses and uphold quality, latency, and cost standards.
• Integrate LLMs with internal data, APIs, and tools via connectors, function calling, and structured outputs.

Skills

Python

LLMs

RAG systems

Vector databases

LangChain

Agent orchestration

JSON outputs

Tools

Pinecone

Qdrant

Milvus

pgvector

Job description

We are looking for a Senior AI Engineer to design and deliver LLM-powered applications and agentic systems that solve real problems for our users and teams. You'll work across the full applied-AI stack — from retrieval-augmented generation (RAG) pipelines and prompt design to multi-step agents that reason, use tools, and automate end-to-end workflows.This is a senior builder's role. You'll take challenging use cases from an ambiguous problem to production: choosing the right models, implementing agentic architectures, wiring up retrieval and tooling, defining how we evaluate quality, and shipping reliable applications at scale.ResponsibilitiesDesign and deliver production LLM applications — chat, copilots, assistants, and autonomous workflows — from concept to scaleBuild and implement RAG pipelines: chunking, embeddings, vector search, reranking, and grounding to reduce hallucination and improve relevanceDevelop agentic architectures: multi-step reasoning, tool/function calling, planning, memory, and multi-agent orchestrationContribute to the automation of business and engineering workflows using agentic AI and workflow automationDefine prompt and context strategies; build evaluation harnesses and uphold quality, latency, and cost standardsIntegrate LLMs with internal data, APIs, and tools via connectors, function calling, and structured outputsImplement guardrails, safety, and observability for AI systems (tracing, evals, monitoring for quality and drift)Collaborate with product, data, and platform teams to turn ambiguous problems into shipped AI featuresShare knowledge with fellow engineers and participate in design reviewsRequirements3+ years in software or ML engineering, including recent, hands-on experience building and shipping applications with LLMsProven experience delivering applied-AI systems end to endProficiency in Python at an advanced levelHands-on background in building RAG systems — embeddings, retrieval, and reranking with vector databases (Pinecone, Qdrant, Milvus, or pgvector)Expertise in LLM APIs and orchestration frameworks (OpenAI, Anthropic, LangChain, or LlamaIndex)Skills in designing agentic architectures — tool use, function calling, planning loops, and agent orchestration in productionCompetency in automating workflows with agentic AI or workflow-automation toolingKnowledge of prompt engineering and structured/JSON output techniquesCapability to design evaluations and reason about LLM quality, cost, and latency trade-offs at scaleExcellent command of written and spoken English (B2+ level)Nice to haveFamiliarity with multi-agent frameworks (LangGraph, CrewAI, or AutoGen)Experience with fine-tuning, adapters (LoRA), or model distillationUnderstanding of MLOps/LLMOps — deployment, versioning, and monitoring of AI systems, including model serving and inference optimizationKnowledge of AI safety, guardrails, and evaluation frameworks (Ragas, LangSmith, or promptfoo)Background in cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes)We offerCONTINUOUS UPSKILLING, LEARNING & DEVELOPMENTDiversity of tasks and projectsAssessment center for objective review of competency levelPersonal development planMentoring programs and leadership developmentCertification and professional development supportAccess to learning platforms including more than 2,500 internal coursesEnglish courses taught by certified teachersCORPORATE BENEFITSExtra leave daysReferral bonusesCOMPENSATION PACKAGECompetitive compensation paid in USDRegular salary and performance reviewsMEDICAL & HEALTHCAREPrivate health insuranceWell-being eventsWORKING ENVIRONMENTRecreation areas and kitchensTea, coffee and snacksSports equipment and game consolesIT EquipmentMicrosoft’s Software Assurance Home Use Program (HUP)Please note that our Talent Attraction Team reviews applications and CVs submitted in English.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.