AI Fullstack Engineer

Title                                 : Senior GenAI Engineer — RAG (Full-Stack)

Experience                    : 5+ years

Location                         : Remote

Work type                      : Chennai - Work from Office/ Remote – Other locations

Employment Type      : Full Time

Notice Period               : Immediate

Work Day                       :Mon to Fri

Key Responsibilities:

• RAG pipeline end to end: ingestion integration, hybrid retrieval with reranking, prompt/context strategy, citation resolution, refusal behavior
• Permission-aware retrieval: source ACL mapping (SharePoint/Entra, Confluence) to fail-closed retrieval filters; zero-leakage test suite partnership with QA
• Vector database design and operations (Milvus or pgvector): schema, metadata filters, sync, performance
• Full-stack product build: React/TypeScript chat and citation experience, Python/FastAPI services, REST APIs, SSO/OIDC integration, admin configuration UI
• Evaluation-driven development: retrieval precision, faithfulness, and citation-accuracy metrics as the daily working loop; A/B testing of retrieval and prompt variants
• Latency engineering to the 3–5s first-token / ~15s complete-answer targets at concurrency

Technical Skills:

• 5+ years software engineering with 2+ years building RAG/LLM applications in production — with real users and real quality metrics, not notebooks
• Deep retrieval craft: chunking strategy, embeddings, hybrid search, rerankers; you can explain why retrieval fails and how you measured the fix
• Genuine full-stack evidence: shipped React/TypeScript front ends AND Python back-end services in production; API design; OIDC/SAML integration
• Vector database production experience (Milvus, pgvector, Weaviate, or equivalent) including permission/metadata filtering
• Evaluation fluency: has built or operated a retrieval/answer quality harness with numeric thresholds

Strongly Preferred:

• Permission-aware/multi-tenant retrieval specifically; Microsoft Graph API; NIM/OpenAI-compatible serving endpoints; streaming UX; enterprise design systems; banking content domains

About Ampera: 

Ampera Technologies, a purpose driven Digital IT Services with primary focus on supporting our client with their Data, AI / ML, Accessibility and other Digital IT needs. We also ensure that equal opportunities are provided to Persons with Disabilities Talent. Ampera Technologies has its Global Headquarters in Chicago, USA and its Global Delivery Center is based out of Chennai, India. We are actively expanding our Tech Delivery team in Chennai and across India. We offer exciting benefits for our teams, such as 1) Hybrid and Remote work options available, 2) Opportunity to work directly with our Global Enterprise Clients, 3) Opportunity to learn and implement evolving Technologies, 4) Comprehensive healthcare, and 5) Conducive environment for Persons with Disability Talent meeting Physical and Digital Accessibility standards 

KEY RESPONSIBILITIES:

•Build agents with persistent context & memory

•Design self-learning feedback loops

•Implement RAG pipelines for domain knowledge

•Manage conversation state & orchestration

•Integrate with LLM APIs (OpenAI, Claude, open-source)

Iterate fast — ship daily, measure weekly

MUST-HAVE SKILLS

•Python / TypeScript proficiency

•LangChain, CrewAI, AutoGen or custom frameworks

•Experience with vector DBs (Pinecone, Weaviate, Qdrant)

•Prompt engineering & evaluation pipelines

•Understanding of agent architectures (ReAct, tool-use)

Git, CI/CD, containerization basics

Role Overview

We are looking for a Python Developer with strong experience in Generative AI and LLM-based applications. The candidate should have hands-on experience building AI solutions using Python, RAG, LangChain/LangGraph, and related GenAI technologies.

Mandatory Skills

Python, GenAI/LLM, RAG, LangChain/LangGraph, Agentic AI, FastAPI, REST API, Vector Database, Prompt Engineering, Microservices

Key Responsibilities

• Develop and maintain applications using Python and modern frameworks.
• Build GenAI/LLM-based applications and solutions.
• Develop RAG pipelines using vector databases.
• Work with LangChain/LangGraph for LLM and agent-based applications.
• Develop and integrate REST APIs using FastAPI.
• Implement Agentic AI workflows and AI-powered features.
• Integrate LLMs with existing applications and microservices.
• Apply prompt engineering techniques to improve AI application performance.

We are building an advanced, AI-driven multi-agent software system designed to revolutionize task automation and code generation. This is a futuristic AI platform capable of:

✅ Real-time self-coding based on tasks  

✅ Autonomous multi-agent collaboration  

✅ AI-powered decision-making  

✅ Cross-platform compatibility (Desktop, Web, Mobile)  

We are hiring a highly skilled **AI Engineer & Full-Stack Developer** based in India, with a strong background in AI/ML, multi-agent architecture, and scalable, production-grade software development.

### Responsibilities:

- Build and maintain a multi-agent AI system (AutoGPT, BabyAGI, MetaGPT concepts)  

- Integrate large language models (GPT-4o, Claude, open-source LLMs)  

- Develop full-stack components (Backend: Python, FastAPI/Flask, Frontend: React/Next.js)  

- Work on real-time task execution pipelines  

- Build cross-platform apps using Electron or Flutter  

- Implement Redis, Vector databases, scalable APIs  

- Guide the architecture of autonomous, self-coding AI systems  

### Must-Have Skills:

- Python (advanced, AI applications)  

- AI/ML experience, including multi-agent orchestration  

- LLM integration knowledge  

- Full-stack development: React or Next.js  

- Redis, Vector Databases (e.g., Pinecone, FAISS)  

- Real-time applications (websockets, event-driven)  

- Cloud deployment (AWS, GCP)  

### Good to Have:

- Experience with code-generation AI models (Codex, GPT-4o coding abilities)  

- Microservices and secure system design  

- Knowledge of AI for workflow automation and productivity tools  

Join us to work on cutting-edge AI technology that builds the future of autonomous software.

Key Requirements / Skills

• 6+ years of overall experience in software development with strong expertise in building scalable web applications.
• 2+ years of experience as a Technical Lead, managing development teams and driving project delivery.
• Strong technical decision-making ability, including architecture design, technology selection, and implementation of best practices.
• Front-end expertise: Strong experience in React, JavaScript, TypeScript, and building responsive and user-friendly UI/UX.
• Back-end development: Hands-on experience with Node.js, RESTful APIs, API design, and server-side architecture.
• Gen AI Expertise: Experience in building RAG & LLM Systems, implementing AI/ML models or integrating AI-based solutions to solve business problems.
• Cloud & DevOps exposure: Experience with AWS/Azure, understanding of CI/CD pipelines, and cloud-based deployments.
• Code quality & best practices: Experience in code reviews, Git version control, and ensuring maintainable and secure code.
• Team leadership: Ability to mentor developers, guide technical discussions, and collaborate across teams.
• Strong communication skills to effectively interact with technical and non-technical stakeholders.
• Experience working in high-compliance environments such as healthcare systems is a plus.

Education Qualifications:

• B.Tech/M.Tech in CSE/IT/AI/ML from a good university

Position: Senior/Lead Full Stack Engineer – Gen AI / Agentic AI

Experience: 7+ Years

Employment: Permanent Position

Location: Banglore / Hyderabad

Job Summary

We are looking for a Senior/Lead Full Stack Engineer – Gen AI / Agentic AI with strong hands-on experience in Python, React.js, MongoDB, Java/Spring Boot and Generative AI/Agentic AI.

The candidate should have experience designing and developing scalable enterprise applications and implementing production-grade LLM, RAG, AI Agent and multi-agent solutions.

Key Responsibilities

• Design, develop and maintain scalable full-stack applications using Python, React.js, MongoDB and Java/Spring Boot.
• Build production-grade Generative AI and Agentic AI applications using LLMs and modern AI frameworks.
• Develop RAG pipelines, AI agents, tool calling, memory management, planning and agent orchestration.
• Work with LangChain, LangGraph, MCP, vector databases and semantic search.
• Develop Python-based APIs, microservices and asynchronous applications using FastAPI/Flask/Django.
• Build REST APIs and event-driven microservices with focus on scalability, performance and resilience.
• Integrate LLMs, embeddings, vector stores and external enterprise tools/services.
• Implement prompt engineering, LLM evaluation, guardrails and AI observability.
• Develop responsive front-end applications using React.js.
• Work with MongoDB, SQL and hybrid data models.
• Implement CI/CD pipelines and support cloud/OCP deployments.
• Follow secure coding, testing, code quality and performance best practices.
• Participate in architecture, technical design, code reviews and mentoring of team members.
• Collaborate with business and technical stakeholders to translate requirements into scalable solutions.

Mandatory Skills

1. Python
2. React.js
3. Gen AI / Agentic AI
4. RAG + LLM
5. LangChain / LangGraph
6. MongoDB
7. Java + Spring Boot
8. REST APIs / Microservices
9. Vector Databases / Embeddings
10. MCP / AI Agent orchestration

Good to Have

• FastAPI / Flask / Django
• Kafka / Solace
• Docker / Kubernetes
• AWS / Azure / GCP / OCP
• CI/CD – Jenkins / GitHub Actions
• LLMOps / AI evaluation / observability
• ELK / Grafana / Splunk / AppDynamics
• SQL / NoSQL
• Agile/Scrum

We are seeking Generative AI Developers with strong Python programming and AI/ML expertise to build, deploy, and optimize LLM-powered applications. The role involves developing RAG solutions, AI agents, and enterprise GenAI applications while collaborating with cross-functional teams.

Key Responsibilities

• Develop and enhance Generative AI applications using LLMs and AI frameworks.
• Build and optimize RAG pipelines, vector search, and AI-powered workflows.
• Design effective prompts and fine-tune models using techniques such as LoRA and QLoRA.
• Develop REST APIs and integrate AI capabilities into enterprise applications.
• Deploy, monitor, and maintain AI solutions in cloud and containerized environments.
• Ensure code quality through testing, debugging, documentation, and code reviews.
• Follow Responsible AI, security, and data governance practices.

Required Technical Skills

• Strong proficiency in Python, OOP, APIs, debugging, and software development best practices.
• Good understanding of Data Structures & Algorithms, complexity analysis, and problem-solving.
• Hands-on experience with LLMs, Prompt Engineering, RAG, AI Agents, and embeddings.
• Experience with LangChain, LangGraph, LlamaIndex, Hugging Face, or similar frameworks.
• Knowledge of vector databases, semantic/hybrid search, and retrieval architectures.
• Experience with PyTorch, TensorFlow, or Keras.
• Familiarity with Docker, Git, CI/CD, and cloud platforms (Azure/AWS/GCP).
• Understanding of AI governance, data privacy, and Responsible AI principles.

Preferred Skills

• Experience with Agentic AI frameworks (CrewAI, AutoGen, Semantic Kernel).
• Exposure to Azure AI Foundry, Databricks, or enterprise AI platforms.
• Knowledge of multimodal AI applications.

Qualifications

• Bachelor's or Master's degree in Computer Science, AI, Data Science, or a related field.
• 5 years of software development experience, including AI/ML or Generative AI projects.
• Experience building and deploying production-grade AI solutions.

Assessment Focus Areas

Candidates will be evaluated on:

• Python coding and problem-solving
• Data Structures & Algorithms
• LLMs, RAG, and Agentic AI concepts
• API development and system design
• Cloud deployment and AI solution architecture

Role & Responsibilities

Responsibilities

• Business: Immerse in operations until you think like an insider.

Rapidly acquire domain expertise through direct observation, translate between business and engineering seamlessly, and mentor engineers in your area on immersion. Influence senior stakeholders effectively, manage complex stakeholder landscapes with competing agendas, and build trust rapidly with new stakeholders.

• Delivery: Lead rapid delivery initiatives across teams in your area, coach on prototype-first approaches, and establish trust through consistent fast delivery. Build complete applications rapidly across any technology stack, select the right tools for each problem, and define clear criteria for prototype-to-production transitions.

• Generative AI: Architect RAG systems for complex use cases across teams, implement advanced techniques (hybrid search, reranking, query expansion), mentor engineers on RAG best practices, and establish RAG standards. Lead evaluation strategy across teams, establishing annotation guidelines, training human-calibrated LLM judges, and building evaluation pipelines that connect tracing to datasets to experiments.

• People: Build high-performing teams across your area, navigate complex interpersonal dynamics, foster psychological safety, and create environments where diverse perspectives are valued. Influence through communication at all levels — from frontline to executive. Handle difficult conversations skilfully and train engineers in your area on effective communication.

• AI-Augmented Development: Optimise AI tool usage across teams in your area, train engineers on AI-augmented and agentic engineering workflows, evaluate new AI development tools, and establish practices that balance AI speed with verification rigour.

• Scale: Design complex multi-component systems end-to-end, evaluate architectural options for large initiatives across teams, guide technical decisions for your area, and mentor engineers on architecture. Create debt reduction strategies across teams, influence roadmap decisions to include debt work, and teach engineers when to accept debt for speed versus when to invest in quality.

• Documentation: Define documentation standards across teams in your area, create documentation systems and templates, train engineers on spec-driven development, and ensure documentation quality across projects. Lead pattern generalization initiatives, defining criteria for when to generalize versus keep custom.

• Reliability: Define reliability standards across teams in your area, drive post-incident improvements systematically, design capacity planning processes, andmentor engineers on SRE practices.

Ideal Candidate

• Strong Staff Software Engineer / FDE profile (full-stack + production GenAI, multi-team technical leadership)
• Mandatory (Experience 1) – Must have 7+ years of relevant professional software engineering experience, with demonstrated full-stack delivery across backend and frontend.
• Mandatory (Experience 2) – Must have deep production experience with Python AND JavaScript/TypeScript, working comfortably across the full stack.
• Mandatory (Experience 3) – Must have 2+ years of experience in generative AI applications developement — LLM integrations, vector databases, RAG systems, and evaluation pipelines
• Mandatory (Experience 4) – Must have strong experience with modern frontend frameworks (Next.js / React) and backend API development.
• Mandatory (Experience 5) – Must have extensive experience with cloud platforms (AWS preferred; Azure/GCP valued), including infrastructure-as-code (CloudFormation / Terraform).
• Mandatory (Experience 6) – Must have working knowledge of multiple database paradigms — relational (PostgreSQL), document, and key-value (Redis) — with ability to select the right storage per problem.
• Mandatory (Experience 7) – Must have strong experience with CI/CD pipelines (e.g. GitHub Actions), containerization, and production deployment strategies.
• Mandatory (Experience 8) – Must have demonstrable fluency with AI coding tools (Claude Code, Cursor, GitHub Copilot, or similar) and proven ability to design agentic engineering workflows and train teams on them
• Preferred (Experience) – Advanced RAG techniques — hybrid search, reranking, query expansion — and establishing RAG standards across teams

Full Stack Developer – AI/ML & GenAI

Location: Mumbai

Experience: 7–9 Years

Employment Type: Full-time

Virtual Drive: Saturday

We are looking for a Python Full Stack Developer with 3+ years of hands-on experience in AI/ML and Generative AI.

Key Skills: Python Full Stack, FastAPI/Flask/Django, React/Angular, AI/ML, GenAI, LLMs, RAG, Embeddings, Vector Databases, Cloud (AWS/Azure/GCP), CI/CD, Docker & Kubernetes.

Full-Stack Engineer (AI-Native) | 2-4 Years Experience

About the Role

We're hiring a Full-Stack Engineer who is equally comfortable building a polished Next.js interface and a reliable NestJS API behind it. You'll build customer-facing products, including AI-powered features like chat interfaces, streaming responses, and agent-driven workflows. You'll own features end to end, from database schema to UI, and use AI tools daily to ship faster without lowering the quality bar.

What You'll Do

Frontend

• Build responsive, accessible, high-performance UIs with React, Next.js (App Router, RSC) and TypeScript
• Build AI-facing interfaces: streaming chat UIs, tool-call/agent-status displays, and loading, error, and retry states for non-deterministic outputs
• Monitor web vitals and fix performance regressions

Backend

• Design and build scalable REST/GraphQL APIs and services with Node.js and NestJS
• Model, query, and optimize data in PostgreSQL (schema design, indexing, migrations) using an ORM like Prisma or Drizzle
• Implement auth, authorization, validation, background jobs, queues, and caching (Redis)
• Integrate LLM APIs (OpenAI, Anthropic, Gemini), including streaming (SSE/WebSockets), tool calling, retries, rate limits, and cost/latency control

AI-Assisted Engineering

• Use AI coding tools (Cursor, Claude Code, Copilot, etc.) for scaffolding, refactoring, debugging, and test writing
• Write and maintain project context for AI tools (rules files, AGENTS.md/CLAUDE.md, reusable prompts) so the whole team gets better output
• Review AI-generated code critically for correctness, security, performance, and maintainability

Team and Delivery

• Write unit, integration, and E2E tests, using AI to speed them up rather than skip them
• Take part in code reviews, sprint planning, architecture discussions, and on-call/incident follow-ups
• Document APIs, decisions, and runbooks clearly

Must-Have (Non-Negotiable)

Frontend

• Strong JavaScript (ES6+) and TypeScript
• React (hooks, state management, rendering behavior) and Next.js (App Router, SSR/SSG/RSC)
• HTML/CSS fundamentals, Tailwind or similar, responsive design, and accessibility basics

Backend

• Production experience with Node.js and a structured framework (NestJS preferred; Express/Fastify with good architecture is fine)
• Solid PostgreSQL skills: relational modeling, joins, indexes, transactions, query optimization
• API design: REST principles, pagination, versioning, error handling, input validation
• Authentication and authorization (JWT, OAuth2, sessions, RBAC)

Engineering Fundamentals

• Git, PR workflows, and code review habits
• Testing across layers (Jest/Vitest, React Testing Library, API/integration tests; Playwright/Cypress is a plus)
• Basic security awareness (OWASP top 10, secrets management, input sanitization)

AI-Assisted Development

• Daily, hands-on use of at least one AI coding tool (Cursor, Claude Code, Copilot, Windsurf, or similar)
• Ability to write clear prompts, give useful context, and break big tasks into steps an AI can handle
• Habit of reviewing, testing, and understanding AI output before committing it
• Basic understanding of how LLMs work: context windows, hallucinations, token cost, and why outputs vary

Nice to Have

• Redis, message queues (BullMQ, SQS, Kafka), or event-driven architecture
• Monorepo tooling (Turborepo, pnpm workspaces, Nx)
• Design system or component library work (shadcn/ui, Radix, Storybook)
• tRPC, GraphQL, or OpenAPI-driven type-safe clients
• Multi-tenant SaaS, payments (Stripe/Razorpay), or real-time features
• Open-source contributions, a side project, or shipped AI features you can demo

What We Expect From You

• Ownership: take a feature from schema to UI to production, and flag risks early
• Judgment over speed: AI makes you faster, and you're still accountable for every line you ship
• Security awareness: no secrets in prompts, no blind copy-paste of AI code, and sensitive data stays out of third-party tools
• Systems thinking: consider scale, failure modes, and cost, not just the happy path
• Learning speed: the AI tooling landscape changes every few months, and you keep up and share what works
• Clear communication: PRs, docs, and async updates that others can follow

If interested for this job pls contact us on this WhatsApp number, nine three one six one two zero one three two