Sr Engineer Python AI

Qtsolv; Mumbai; Hybrid; INR 3,000,000 - 6,000,000; Full time

Job summary

Qtsolv in Mumbai is seeking a senior Backend & Core (Python) engineer to design and maintain high-scale REST and WebSocket services using FastAPI, async SQLAlchemy, PostgreSQL, and Redis. You will work in a convention-driven codebase and contribute to AI/LLM integration.

Responsibilities include building agent-enabled tooling, ensuring security, scalability, and resilient data pipelines, plus collaborating with remote teams across timezones. Experience with SOC 2 compliance is valued.

Qualifications

• 5+ years of experience in software engineering.
• 3+ years of experience in a SaaS organization.
• 3+ years Python backend, ideally async FastAPI/SQLAlchemy.
• Hands-on LLM/agent-building experience.
• RAG implementation experience is a differentiator.
• Experience with event-driven architectures using message brokers (SQS)
• Experience integrating LLM/RAG capabilities into production applications.
• Experience with SOC 2 or similar compliance frameworks.
• Experience working remotely with distributed teams across timezones.

Responsibilities

• Design, build, and maintain efficient, reusable, reliable, and scalable FastAPI services — REST + WebSocket APIs backed by PostgreSQL and Redis.
• Own and evolve the APIs supporting web clients and the mobile layer — contract design, versioning, and backward compatibility.
• Build and maintain background jobs, schedulers, batch/cron tasks, and event consumers/publishers across RabbitMQ and SQS.
• Uphold multi-tenant architecture principles and tenant-scoped data access across all backend work.
• Identify performance bottlenecks and develop solutions in a high-traffic multi-tenant SaaS environment.
• Build and maintain LLM-powered features — LangChain/OpenAI orchestration, MCP tool integrations, and RAG pipelines over pgvector/FAISS.
• Own embedding, retrieval, and prompt strategies; monitor quality, latency, and token cost.
• Build and iterate on real tool-calling agents using agent frameworks (Bedrock AgentCore or equivalent).
• Implement guardrails and LLM safety configuration in production paths.
• Design and maintain queue/async job patterns for decoupled agent worker execution.
• Translate business requirements into backend and AI solutions spanning FastAPI services and agentic layers.
• Create design documents and maintain architecture documentation.

Skills

Python

FastAPI

Async SQLAlchemy

PostgreSQL

Redis

WebSocket

API security

LLM integration

Agent framework

AWS SQS

Distributed systems

CICD

Remote collaboration

Job description

Skills Required

Backend & Core (Python)

• Proficiency in Python3.13, async/await — async-first codebase (SQLAlchemy w/asyncpg/psycopg[binary]); minimal tolerance for sync code
• Advanced knowledge ofFastAPI — routes, dependency injection, Pydantic v2 schemas, exception handlers
• SQLAlchemy 2.0 (asyncORM) — rich domain models, business logic on the model layer (notrepository/service wrappers)
• Advanced knowledge ofAPI security, authentication and authorization
• Experience developingRESTful web APIs and real-time WebSocket services
• Familiarity withbackground job, queue, and task scheduling frameworks: APScheduler and AWS SQS(boto3)
• Advanced knowledge ofdata structures and algorithms with attention to time/space complexity
• PostgreSQL — schemadesign and hand-written idempotent SQL migrations (no ORM migration tooling)
• Comfort working within astrongly convention-driven codebase (documented architectural standards, nottribal knowledge)

AI / LLM Integration

• Agent frameworkexperience — building agents, tool-calling loops, model configuration
• Model Context Protocol(MCP) — hands-on experience building or exposing MCP tools/servers, includinghow tool metadata (names/descriptions) shapes what an LLM sees
• AWS Bedrock — modelinvocation, plus familiarity with agent runtime deployment patterns(containerized, separate from core API/worker infra)
• Prompt engineering &lifecycle management — designing prompts that work consistently across multipledelivery mechanisms (template-based vs. managed prompt services)
• Guardrails — experiencewith LLM safety/guardrail configuration in production paths
• Queue/async job design —decoupled worker patterns (SQS/Redis-class tooling); understanding jobdispatch, retries, DLQ semantics
• Experience integratingLLMs via the OpenAI SDK and prompt orchestration, tools/agents, and tokenbudgeting

Database & Caching

• Advanced knowledge ofSQL and PostgreSQL
• Experience with databaseperformance tuning, query optimization, and connection-pool sizing
• Proficiency with Redisfor caching, session/state storage, and ephemeralik coordination
• Understanding offundamental design principles behind scalable, high-performing applications andhow they fit into a larger microservices/distributed system
• Understanding ofmulti-tenant architecture — tenant isolation, data segregation, andshared-infrastructure patterns
• Understanding ofasynchronous and event-driven processing, publish/subscribe, at-least-oncedelivery, dead-letter handling, idempotency, and eventual consistency
• Familiarity withresilience patterns — circuit breakers, retries with back-off, and gracefuldegradation across service boundaries

Platform Conventions to Onboard

• Queue-drivenarchitecture (API enqueues, worker dispatches — no direct execution)
• Config-driven systemdesign (DB-backed operational config with fallback defaults)
• Working within a sharedinternal scaffolding/template system and layered documentation set

Infrastructure & DevOps

• Experience with CI/CDvia Bitbucket Pipelines and artifact management
• Familiarity with AWSservices: S3, SQS, SES, STS and similar
• Familiarity withmonitoring/observability tooling (Splunk experience a plus)
• Familiarity withsecurity scans, penetration tests, and vulnerability remediation
• Familiarity with theAtlassian suite: Jira, Confluence, Bitbucket
• Experience with Gitbranching strategies, pull-request workflows, and code review practices
• Experience working inremote and async-first collaboration environments

Nice-to-Have / Seniority-Gated

• Auth internals(Cognito-based auth, JWT scope middleware) — only for engineers touchingauth/registration flows
• AWS deploymentfamiliarity (SQS/S3/ECS Fargate) — abstracted by internal tooling, so lowerpriority
• Experience withlightweight local agent-testing UIs (e.g., Chainlit) — low priority

Experience Requirements

• 5+ years of experiencein software engineering
• 3+ years of experiencein a SaaS organization
• 3+ years Python backend,ideally async FastAPI/SQLAlchemy specifically (not just Flask/Django syncexperience)
• Hands-onLLM/agent-building experience (built and iterated on real tool-calling agents —framework itself matters less than depth)
• RAG implementationexperience (vector store + retrieval) is a strong differentiator
• Experience withevent-driven architectures using message brokers and/or cloud queues (SQS)
• Experience integratingLLM/RAG capabilities into production applications is a strong plus
• Experience with SOC 2 orsimilar compliance frameworks
• Experience workingremotely with distributed teams across timezones

Hiring signal:

Candidates with real MCP experience (not just generic"function calling") and exposure to managed agent runtimeenvironments (e.g., Bedrock AgentCore or equivalent) will ramp faster thangeneralist LLM-app engineers.

Tasks & Responsibilities

• Design, build, andmaintain efficient, reusable, reliable, and scalable FastAPI services — REST +WebSocket APIs backed by PostgreSQL and Redis
• Own and evolve the APIssupporting web clients and the mobile layer — contract design, versioning, andbackward compatibility
• Build and maintainbackground jobs, schedulers, batch/cron tasks, and event consumers/publishersacross RabbitMQ and SQS
• Uphold multi-tenantarchitecture principles and tenant-scoped data access across all backend work
• Identify performancebottlenecks and develop solutions in a high-traffic multi-tenant SaaSenvironment
• Build and maintainLLM-powered features — LangChain/OpenAI orchestration, MCP tool integrations,and RAG pipelines over pgvector/FAISS
• Own embedding,retrieval, and prompt strategies; monitor quality, latency, and token cost
• Build and iterate onreal tool-calling agents using agent frameworks (Bedrock AgentCore orequivalent)
• Implement guardrails andLLM safety configuration in production paths
• Design and maintainqueue/async job patterns for decoupled agent worker execution
• Translate businessrequirements into backend and AI solutions spanning FastAPI services andagentic layers
• Create design documentsfrom software requirements and maintain architecture documentation
• Apply scalability andresilience methodologies (caching, queuing, circuit breaking) in a consistentand robust manner
• Define and evolvebackend engineering standards (API contracts, state boundaries, agent patterns)as the team scales

Security & Compliance

• Identify and remediatecommon API vulnerabilities within defined SLAs
• Participate in quarterlySOC 2 compliance activities including static, dynamic, and 3rd-party libraryscans
• Apply security-firstdevelopment practices and dependency hygiene across the stack
• Support incidentresponse and troubleshooting for enterprise clients within defined SLAs
• Use structured logs fordiagnosis and post-incident review
• Identify root causes andimplement permanent fixes for production issues
• Collaborate closely withthe US-based oversight engineer, the technical architect, and peer engineers
• Participate in codereviews and establish code-quality standards
• Mentor and guide mid-level engineers as the team scales
• Work effectively in aremote, async-first environment across timezones