Architect / Principal Software Engineer — AI Solution Engineering

EPAM Systems, Inc.; United States; Remote; USD 150,000 - 190,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Upskilling & certification courses

LinkedIn Learning access

Job summary

EPAM Systems, Inc. is seeking an Architect / Principal Software Engineer to define technical direction across AI engineering pods, building production-grade agentic systems and ensuring reliability, speed, and security.

This hands-on role balances architecture with mentorship, requiring deep expertise in Python, FastAPI, LangChain, and AWS, and involves drafting standards, design reviews, and guiding cross-functional teams.

Qualifications

• 10+ years of software engineering experience building distributed backend systems.
• 6+ years Python experience with FastAPI, AsyncIO, and modern typing.
• 3+ years production LLM systems experience using LangChain and related agent frameworks.
• Hands-on solution architecture balancing cost, latency and operability.
• Strong AWS experience with container and serverless services.
• Solid security fundamentals including OAuth 2.0, OIDC and secret handling.
• Excellent code review and mentorship for senior engineers.
• Upper-Intermediate English proficiency.

Responsibilities

• Set architectural direction across multiple AI pods and document trade-offs.
• Design predictable multi-agent workflows with streaming responses and low latency.
• Build backend AI services and reference implementations, coding 30–40% of the time.
• Define orchestration patterns and integration contracts with frontend teams.
• Establish standards for Model Context Protocol servers, tool schemas, and context management.
• Mentor senior engineers through design reviews and guidance.

Skills

Distributed backend

Python (FastAPI AsyncIO)

LangChain integration

AWS cloud native

Security fundamentals

Code review & mentorship

Cross-team collaboration

English communication

Tools

LangChain

OpenSearch

Pinecone

Qdrant

Job description

We are looking for an Architect / Principal Software Engineer to build production-grade agentic systems and need a hands-on architect to set technical direction across AI engineering pods. You will balance architecture, standards, and mentorship with prototyping core workflows and reviewing code to keep systems reliable, fast, and secure.ResponsibilitiesSet architectural direction across multiple AI pods and document trade-offs across capability, cost, latency, and complexityDesign predictable multi-agent workflows with streaming responses, low latency, and robust error handlingBuild backend AI services and reference implementations, spending 30%–40% of time writing and reviewing codeDefine orchestration patterns and integration contracts for clean collaboration with frontend teamsEstablish shared standards for Model Context Protocol servers, tool schemas, and context managementPartner with Security and Infrastructure to enforce least-privilege execution, tenant isolation, and secure secret handlingDefine observability requirements and service-level objectives, including tracing for agent workflowsMentor senior engineers through design reviews, technical guidance, and standards adoptionRequirements10+ years of software engineering experience building distributed backend systems6+ years of Python experience with FastAPI, AsyncIO, and modern typing3+ years of production LLM systems experience using LangChain and related agent frameworksHands-on solution architecture skills balancing cost, latency, and operabilityStrong AWS experience with container and serverless services and managed AI offeringsSolid security fundamentals knowledge including OAuth 2.0, OIDC, and secret handlingStrong code review and mentorship skills supporting senior-level engineersClear cross-team communication skills with Product, Security, Data, and Infrastructure partnersUpper-Intermediate English proficiency (B2)REST API design experience defining stable integration contractsNice to haveModel Context Protocol server implementation experienceTerraform infrastructure-as-code experienceVector databases experience such as OpenSearch, Pinecone, or QdrantVector retrieval migration experience from legacy retrieval systemsWe offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedIn