Solution Architect – Python with GenAI

EPAM Systems, Inc.; Hyderabad; Hybrid; INR 3,000,000 - 6,000,000; Full time

Job summary

EPAM Systems, Inc. is seeking a Solution Architect with deep Python and Generative AI expertise to design and deliver enterprise GenAI solutions for production environments.

You will lead architectural design, drive experiments, and collaborate across teams to ensure scalable, reliable LLM-based applications, including MLOps and cloud deployment with AWS/Azure/GCP, Docker, and Kubernetes.

Qualifications

• 9–14 years in software development with solution architecture and system design.
• Expert-level Python for production-grade code delivery.
• Experience with microservices, architectural patterns, FastAPI, Redis, Elasticsearch and Kafka.
• Hands-on GenAI development across Agents, RAG, and GraphRAG concepts.
• Familiarity with LangGraph, LangChain and orchestration platforms.
• Experience evaluating LLMs and managing prompts; production-focused GenAI delivery.
• Cloud exposure across AWS, Azure or GCP and containerization with Docker/Kubernetes.
• Awareness of vector databases (Pinecone, Weaviate, Chroma) and LLMOps basics.
• Proven leadership for guiding engineering teams and client-facing collaboration.
• Strong English communication skills (written and spoken).

Responsibilities

• Design full-scale GenAI architecture solutions including RAG models and multi-agent frameworks.
• Produce reusable accelerator components and reference architectures for consistency.
• Lead technical discovery sessions and provide practical support to engineering teams.
• Build evaluation frameworks and establish standards for LLM applications.
• Collaborate across teams to ensure scalable, sustainable architecture.
• Develop microservices-based systems using established patterns and modern frameworks.
• Guide the integration of cloud infrastructure across AWS, Azure, or GCP.
• Manage container deployment and orchestration with Docker and Kubernetes.
• Evaluate vector database options (Pinecone, Weaviate, Chroma) for GenAI projects.
• Implement LLMOps strategies and monitoring to improve production rollout quality.
• Support prompt engineering and RAG evaluation to improve reliability.
• Mentor on architecture and contribute knowledge across the function.
• Enforce strong coding standards for production-grade Python development.

Skills

Python production

Microservices design

FastAPI

Redis

Elasticsearch

Kafka

GenAI development

LangChain

LLMOps fundamentals

Client facing

Tools

Docker

Kubernetes

AWS

Azure

GCP

Job description

Our expanding team is on the lookout for a Solution Architect focused on Python and Generative AI, responsible for engineering and delivering enterprise-caliber GenAI solutions built to perform in live production settings. As a member of our Solution Architecture team, you'll direct technical research initiatives, produce reusable tools, and help define standards for applications built around LLMs.

Responsibilities

• Design full-scale GenAI architecture solutions, including RAG models, Agents, and Multi-Agent frameworks, built for large-scale enterprise use.
• Produce reusable accelerator components and reference architectures to bring uniformity to solution delivery.
• Lead technical discovery sessions and deliver direct, practical support to engineering teams.
• Build evaluation frameworks and define standards that shape how LLM applications are developed.
• Collaborate with a range of teams to ensure architectural designs scale appropriately and remain sustainable long-term.
• Develop microservices-based systems by applying established patterns and current-generation frameworks.
• Guide the integration of cloud infrastructure elements across environments like AWS, Azure, or GCP.
• Manage container-based deployment and orchestration efforts through Docker and Kubernetes.
• Evaluate and pick suitable vector database options, such as Pinecone, Weaviate, or Chroma, for supporting GenAI projects.
• Implement LLMOps strategies and monitoring tools to strengthen the quality of production rollouts.
• Support prompt engineering and RAG evaluation activities aimed at improving application reliability.
• Participate in mentoring initiatives and contribute knowledge across the architecture function.
• Enforce strong coding standards for production-level Python development.
• Lead efforts toward ongoing refinement of system architecture and solution scalability.

Requirements

• A range of 9 to 14 years working in software development, with solid grounding in solution architecture and system design.
• Expert-level Python skills geared toward delivering code suitable for production.
• Capability across microservices design, architectural patterns, FastAPI, Redis, Elasticsearch, and Kafka.
• Extensive hands-on background in GenAI application development, spanning Agents, MCP, RAG, Agentic RAG, and GraphRAG.
• Deep familiarity with LangGraph, LangChain, and similar orchestration platforms.
• Applied experience assessing LLMs and RAG systems while overseeing prompt management.
• Established success delivering GenAI applications that scale well in production settings.
• Hands-on background using cloud platforms like AWS, Azure, or GCP.
• Comfort working with containerization technologies, specifically Docker and Kubernetes.
• Awareness of vector database solutions, including Pinecone, Weaviate, or Chroma.
• Firm grasp of LLMOps fundamentals and the monitoring tools that support them.
• Demonstrated leadership skill suited for steering engineering teams.
• Comfortable operating in client-facing capacities while maintaining strong team collaboration.
• Strong English skills, covering both writing and speaking, at B2 level or above.
• Nice to have Background in traditional machine learning work, covering feature engineering, model training, and evaluation practices.
• Understanding of knowledge graph concepts along with fine-tuning techniques.
• Prior experience in consulting roles or positions involving direct client engagement.