AI Generative Full Stack Developer

Bounteous; India; On-site; INR 1,200,000 - 1,900,000; Full time

Job summary

Bounteous is seeking an AI Generative Full Stack Developer to design, build, and deploy intelligent AI-powered applications, combining generative AI with robust full stack development using Python and React. You will work at the intersection of AI research and product engineering, turning LLM capabilities into production-ready features.

Design and develop AI-powered applications, build agentic frameworks, integrate AI APIs, and craft end-to-end solutions across backend and frontend.

Qualifications

• Hands-on experience with Claude API and Anthropic SDK, including tool use and token budgeting.
• Designing reliable multi-step agent loops with tool orchestration and error handling.
• Building and connecting tools via internal/external APIs with robust validation.
• Proficient in prompt engineering, structured prompts, and eval harnesses.
• Ability to log and audit agent traces in a queryable format (LangSmith, Helicone).
• Define meaningful agent metrics: task completion rate, latency, cost, accuracy.
• Know when to apply human-in-the-loop gates for high-stakes actions.
• Profile and reduce inference costs with caching, batching, and tiering.
• Security and data handling, including PII and least-privilege access.
• Strong async Python/TypeScript, testing, CI/CD, and modular design.

Responsibilities

• Design and develop AI-powered full stack applications using Python, React.
• Build agentic frameworks and LLM pipelines with LangChain or custom solns.
• Integrate generative AI APIs (OpenAI, Anthropic, Gemini) into web apps.
• Develop RESTful and GraphQL APIs to connect AI backends with frontends.
• Create prompt engineering workflows and evaluation pipelines.
• Collaborate with product, design, and data science to ship features end-to-end.
• Write clean, tested, documented code; monitor AI model performance in production.
• Stay updated with evolving generative AI landscape.

Skills

Claude API proficiency

Agentic loop architecture

Tool/MCP integration

Prompt engineering

Observability & auditability

Metrics & KPI design

Human-in-the-loop & guardrails

Cost & latency optimization

Security & data handling

Software engineering fundamentals

Tools

LangChain

LlamaIndex

OpenAI API

Anthropic Claude

LangSmith

Braintrust

Helicone

Celery

Redis

PostgreSQL

MongoDB

Docker

Kubernetes

FastAPI

Django

Flask

Job description

5 to 9 years of experience Skills: AI Generative Full Stack Developer

AI Generative Full Stack Developer

Mode of Work: Hybrid

Employment Type: Full-time

About the Role

We are looking for a talented and passionate AI Generative Full Stack Developer to join our growing engineering team. You will be responsible for designing, building, and deploying intelligent AI-powered applications — combining cutting‑edge generative AI capabilities with robust full stack development using Python and React .

You will work at the intersection of AI research and product engineering, turning LLM capabilities into real-world, production-ready features.

Key Responsibilities

• Design and develop AI-powered full stack applications using Python (backend) and React (frontend)
• Build and maintain agentic frameworks and LLM pipelines using tools like LangChain, LlamaIndex, or custom implementations
• Integrate generative AI APIs (OpenAI, Anthropic Claude, Gemini, etc.) into scalable web applications
• Develop RESTful and GraphQL APIs to connect AI backends with React frontends
• Build and optimize prompt engineering workflows and evaluation pipelines
• Collaborate with product, design, and data science teams to ship AI features end‑to‑end
• Write clean, testable, and well‑documented code
• Monitor, debug, and optimize AI model performance in production
• Stay current with the rapidly evolving generative AI landscape

Required Skills & Experience

• Claude API & Anthropic SDK proficiency — Hands‑on experience with the Messages API, tool use / function calling, system prompt design, and model selection tradeoffs (Sonnet vs. Opus vs. Haiku). Familiarity with context window management and token budgeting.
• Agentic loop architecture — Ability to design reliable multi‑step agent loops: tool orchestration, retry logic, error recovery, and knowing when to stop or elevate rather than loop indefinitely.
• Tool/MCP integration — Experience building and connecting tools (internal APIs, databases, external services) via Anthropic's tool use schema or MCP servers, including input validation and graceful failure handling.
• Prompt engineering & evaluation — Skilled at structured prompting (system prompts, few‑shot examples, XML tagging), and building prompt eval harnesses to measure output quality, regression‑test changes, and tune instructions systematically.
• Observability & auditability — Knows how to log full agent traces (inputs, tool calls, intermediate outputs, final responses) in a structured, queryable format. Experience with tools like LangSmith, Braintrust, Helicone, or custom tracing pipelines.
• Measurement & KPI design — Can define and instrument meaningful agent metrics: task completion rate, tool call accuracy, hallucination rate, latency per step, cost per run, and human‑in‑the‑loop escalation rate. Connects agent telemetry to business outcomes.
• Human‑in‑the‑loop & guardrails — Understands when to inject human review checkpoints, how to design approval gates for high‑stakes actions, and how to implement input/output guardrails (content filtering, schema validation, confidence thresholds).
• Cost & latency optimization — Experience profiling and reducing inference costs through prompt caching, batching, streaming, and appropriate model tiering — without sacrificing reliability.
• Security & data handling — Awareness of prompt injection risks, credential/secret hygiene in agentic contexts, PII handling, and least‑privilege design when agents have access to real systems or external APIs.
• Software engineering fundamentals — Strong async Python (or TypeScript), testing discipline (unit + integration tests for agent components), CI/CD, and the ability to decompose complex agent systems into maintainable, modular code.

AI / LLM

• Hands‑on experience with LLM APIs (OpenAI, Anthropic, Cohere, or similar)
• Experience building agentic systems (tool use, memory, multi‑step reasoning)
• Familiarity with prompt engineering techniques (chain‑of‑thought, few‑shot, RAG)
• Understanding of fine‑tuning and model evaluation concepts
• Strong proficiency in Python 3.x
• Experience with FastAPI or Django / Flask
• Working knowledge of SQL and NoSQL databases (PostgreSQL, MongoDB, Redis)
• Familiarity with async programming and background task queues (Celery, RQ)
• Experience with Docker and deploying to cloud platforms (AWS, GCP, or Azure)

Frontend (React)

• Experience with TypeScript
• Familiarity with state management (Redux, Zustand, or Context API)
• Ability to build streaming UI for LLM outputs (token‑by‑token rendering)
• Basic understanding of UX principles for AI interfaces

General

• Experience with Git and collaborative development workflows
• Comfort working in fast‑paced, ambiguous environments
• Strong problem‑solving and communication skills

Nice to Have

• Certified Claude Architect – Foundations (CCA‑F)
• Experience with Claude Code, Cursor, or other AI‑assisted development tools
• Contributions to open‑source AI projects
• Experience with multi‑agent frameworks (AutoGen, CrewAI, LangGraph)
• Knowledge of MLOps practices and model deployment (MLflow, Weights & Biases)
• Familiarity with WebSockets for real‑time AI streaming
• Experience with Kubernetes or serverless architectures

We understand technologists. We know what gets them excited. There's plenty of opportunity here and lots of new technology that we're exploring. Over time your interests will change, the things that excite you will change, and the technology will change, but what stays the same for Bounteous is creating growth opportunities for our team and our relentless pursuit to create transformative digital experiences.