Python AI Engineer

EPAM Systems; California; Hybrid; USD 93,000 - 107,000; Full time

Benefits offered by this job

Extended Health care

Dental and Vision

RRSP with Company match

Employee Stock Purchase Program

Telehealth

Life and AD&D Insurance

Employee Assistance Program

Job summary

EPAM Systems Inc is seeking a Python AI Engineer to build scalable AI infrastructure for an enterprise knowledge platform, evolving from Confluence-focused RAG to a broader agentic system. You will design and implement robust backend services with FastAPI, LangGraph, and modern retrieval pipelines, while ensuring observability and compliance across the stack.

The role focuses on production-grade agent runtime, grounding accuracy, and cost-conscious performance, with strong collaboration across

Qualifications

• Strong, hands-on Python experience in platform, automation, or infrastructure-heavy environments.
• Experience building CLI tools using Python, Golang, or Rust.
• Hands-on experience with LangGraph, LangChain, pgvector, and modern retrieval pipelines.
• Experience designing evaluation frameworks for LLM-backed systems, including regression detection and quality measurement.
• Strong experience with Docker, Helm, GitHub Actions, and Kubernetes-oriented workflows.

Responsibilities

• Architect and implement robust backend services using Python 3.11, FastAPI, Pydantic, SQLAlchemy async, and asyncpg.
• Design trade-offs around retrieval quality, latency, cost, safety, and operational simplicity.
• Build production-grade agent runtime capabilities, including memory boundaries, tool sandboxing, permissions, and budget controls.
• Improve answer grounding, failure analysis, and citation enforcement for enterprise-grade dependability.
• Create comprehensive observability and operational feedback loops using OpenTelemetry, Prometheus/Grafana, Docker/Helm, and GitHub Actions.
• Ingestion infrastructure across current and future content sources.
• Full-stack observability across application, pipeline, database, and model-serving behavior.
• Cost, latency, throughput, and failure-mode management for AI-heavy workloads.
• Release workflows that validate AI behavior changes, not just code compilation.
• Partner with product and engineering teams to support multiple conversational surfaces through a unified knowledge platform.

Skills

Python

LangGraph

LangChain

pgvector

Retrieval pipelines

Docker

Kubernetes

GitHub Actions

Observability

ETL

Tools

FastAPI

SQLAlchemy async

asyncpg

Job description

We are hiring a Python AI Engineer to operate and evolve the infrastructure behind an enterprise knowledge base platform as it transitions from a Confluence-focused RAG chatbot into a broader, agentic knowledge system.Today, our platform supports Confluence/GitHub ingestion chunking pgvector RAG retrieval FastAPI serving. In our next growth phase, we are expanding toward hybrid retrieval (vector + sparse + graph), multi-source ingestion, robust evaluation pipelines, agent infrastructure, and shared chat platform primitives.If you are passionate about building scalable, reliable, and production-grade AI infrastructure rather than just chasing demo behavior, we want to hear from you.Req.#1093687315The recruiting efforts for this position are intended to fill an existing vacancy for a new position.ResponsibilitiesArchitect and implement robust backend services using Python 3.11, FastAPI, Pydantic, SQLAlchemy async, and asyncpgDesign trade-offs around retrieval quality, latency, cost, safety, and operational simplicityBuild production-grade agent runtime capabilities, including memory boundaries, tool sandboxing, permissions, and budget controlsImprove answer grounding, failure analysis, and citation enforcement for enterprise-grade dependabilityCreate comprehensive observability and operational feedback loops using OpenTelemetry, Prometheus/Grafana, Docker/Helm, and GitHub ActionsIngestion infrastructure across current and future content sourcesFull-stack observability across application, pipeline, database, and model-serving behaviorCost, latency, throughput, and failure-mode management for AI-heavy workloadsRelease workflows that validate AI behavior changes, not just code compilationPartner closely with product and engineering teams to support multiple conversational surfaces through a unified knowledge platformRequirementsStrong, hands-on Python experience in platform, automation, or infrastructure-heavy environmentsExperience building CLI tools using Python, Golang, or RustHands-on experience with LangGraph, LangChain, pgvector, and modern retrieval pipelinesExperience designing evaluation frameworks for LLM-backed systems, including regression detection and quality measurementStrong experience with Docker, Helm, GitHub Actions, and Kubernetes-oriented workflowsSystems Understanding: Familiarity with the operational characteristics of embedding pipelines, vector search, and LLM-backed systemsStrong skills across metrics, tracing, dashboards, alerting, and log analysisExperience with ingestion, ETL, or content-processing pipelines at scaleAn innate ability to think in terms of reliability, cost, latency, throughput, and disaster recoveryNice to haveExperience with Qdrant, Neo4j, or other vector/graph infrastructurePrior experience supporting RAG, search, evaluation, or agent platformsBackground in enterprise or highly regulated environmentsFamiliarity with enterprise tooling such as Vault, Splunk, Artifactory, or ECRComfort leveraging AI-assisted engineering workflows in day-to-day workWe offerExtended Healthcare with Prescription Drugs, Dental and Vision, and Healthcare Spending Account (Company Paid)Life and AD&D Insurance (Company Paid)Employee Assistance Program (Company Paid)Telehealth (Company Paid)Short-term Disability (Company Paid)Long-Term DisabilityPaid Time Off (including vacation and sick days)Registered Retirement Savings Plan (RRSP) with Company matchMaternity/Parental/Adoption Leave Top-upEmployee Stock Purchase ProgramCritical Illness InsuranceEmployee DiscountsUnlimited access to LinkedIn learning solutionsEPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our clients, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.Engineer the Future with a Career at EPAMThis posting includes a salary range EPAM Canada would reasonably expect to pay the selected candidate. Individual compensation offers within the range are based on a variety of factors, including, but not limited to, experience, credentials, education, training, the demand for the role, skillset, and overall business and local labour market considerations. Most candidates are hired at a salary within the range disclosed. Salary range: CA$130,000-CA$150,000. In addition, the details highlighted in this job posting above are a general description of all other expected benefits and compensation for the position.EPAM Canada welcomes and encourages applications from candidates with disabilities. Please contact WFA Human Resource CA [e-mail] if you have questions in this regard, or if you require an accommodation to complete the application process. Click here to review EPAM’s Accessibility for Ontarians with Disabilities Accessibility Policies and Multi-Year Access.An artificial intelligence system is software that is developed with one or more techniques that can, for a given set of human-defined objectives, using algorithmic information processing, generate outputs such as content, predictions, recommendations, or decisions with varying levels of autonomy (“AI”). Tasks that humans have traditionally done by thinking and reasoning are increasingly being done by, or with the help of, AI to help create efficiencies.EPAM may use AI during the recruitment process, in connection with collecting or processing your personal data. Some (non-exhaustive) examples of tasks that EPAM may use AI for include conducting initial screening, creating transcripts of interviews, and assessing applications/CVs against defined job description criteria to make suggestions to the individuals evaluating your candidacy.Your personal data and the results of any processing are not shared with AI applications outside of EPAM infrastructure. While EPAM may use AI to help create efficiencies during the recruitment process, EPAM does not use AI to make hiring decisions, which is done by EPAM Talent Acquisition and management.