Forward Deployed Engineer – Full Stack & Agentic AI

Location: Hyderabad, Telangana, India Job Type: Full-time

Experience: 5–10 years

Compensation: ₹15,00,000–₹30,00,000 per annum

Work Model: [On-site]

About the Role

We are looking for a hands-on Forward Deployed Engineer with strong full-stack development experience and a proven background in Agentic AI, Retrieval-Augmented Generation (RAG), and AI-powered product development. In this role, you will work closely with customers, product managers, and engineering teams to design, build, deploy, and improve intelligent software solutions. You will translate real-world business requirements into scalable products using modern web technologies, LLMs, AI agents, and cloud platforms.

This is an ideal opportunity for an engineer who enjoys solving complex customer problems, working across the technology stack, and rapidly moving AI products from concept to production.

Key Responsibilities

- Design and develop end-to-end full-stack applications for customer and business use cases.
- Build and deploy Agentic AI systems, AI assistants, workflow automation, and multi-step reasoning applications.
- Develop high-performance RAG pipelines, including document ingestion, chunking, embeddings, vector search, retrieval, reranking, and response generation.
- Work with OpenAI APIs, LLMs, function calling, tool use, structured outputs, and prompt engineering.
- Integrate AI agents with internal systems, APIs, databases, SaaS tools, and enterprise workflows.
- Build reliable backend services, APIs, data pipelines, and frontend interfaces.
- Collaborate directly with customers and stakeholders to understand requirements and deliver practical solutions.
- Rapidly prototype, test, and iterate on current product ideas and AI capabilities.
- Deploy and operate production systems with appropriate monitoring, logging, security, and performance controls.
- Evaluate model quality, latency, cost, reliability, and user experience.
- Troubleshoot technical issues across application, infrastructure, data, and AI layers.




- Contribute to architecture decisions, engineering standards, documentation, and product strategy.
- Support the full product development lifecycle, from discovery and design through deployment and continuous improvement.

Required Qualifications

- 5–10 years of professional software engineering experience.
- Strong experience in full-stack development.
- Proficiency in one or more backend languages such as Python, Node.js, Java, Go, or similar.
- Experience building frontend applications using technologies such as React, Next.js, Angular, or Vue.js.
- Strong understanding of REST APIs, microservices, databases, authentication, and cloud deployments.
- Hands-on experience developing applications using OpenAI APIs or other large language model platforms.
- Practical experience with RAG systems, vector databases, embeddings, semantic search, and knowledge retrieval.
- Experience designing or implementing AI agents, agent workflows, tool calling, or autonomous task execution systems.
- Familiarity with relational and NoSQL databases such as PostgreSQL, MySQL, MongoDB, Redis, or similar.
- Experience with Git, CI/CD, Docker, and cloud platforms such as AWS, Azure, or Google Cloud.
- Strong problem-solving, communication, and stakeholder-management skills.
- Ability to work independently in a fast-moving product development environment.

Preferred Qualifications

- Experience with frameworks and tools such as LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or similar agent frameworks.
- Experience building fast and scalable RAG solutions, including FastAPI, hybrid search, reranking, caching, and retrieval optimization.




- Experience with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, Chroma, Elasticsearch, or pgvector.
- Experience with AI evaluation, observability, guardrails, prompt versioning, and model monitoring.
- Experience working directly with customers in a consulting, solutions engineering, startup, or forward-deployed engineering role.
- Experience taking AI products from prototype to production.
- Familiarity with Kubernetes, Terraform, serverless infrastructure, or cloud-native architecture.
- Knowledge of data privacy, security, responsible AI, and enterprise application integration.
- Experience working with product analytics, experimentation, and user feedback.

What We Offer

- Competitive compensation of ₹15–30 lakhs per annum, based on experience and technical expertise.
- Medical insurance coverage.
- Provident Fund benefits.
- Opportunity to work on practical, production-grade Agentic AI and RAG applications.
- Direct exposure to customers, product strategy, and end-to-end technology decisions.
- A collaborative, fast-paced, and entrepreneurial work setting.
- Opportunities for professional growth and ownership of meaningful projects.

Ideal Candidate

You are a product-minded engineer who can move comfortably between customer conversations, system architecture, backend development, frontend implementation, and AI experimentation. You enjoy working with ambiguity, delivering quickly, and turning emerging AI capabilities into reliable products that solve real business problems.

How to Apply

Please submit your resume along with:
- Examples of full-stack or AI products you have built.
- Details of your experience with RAG, OpenAI APIs, or Agentic AI systems.
- Links to GitHub, portfolio, technical articles, or relevant projects, if available.
- Your current location, notice period, and expected compensation.

Pay: ₹1,500,000.00 - ₹3,000,000.00 per month

Benefits

- Health insurance
- Paid sick time
- Provident Fund

Work Location: In person

📌 Forward Deployed Engineer – Full Stack & Agentic AI (Hyderabad)
🏢 Avantao Technologies
📍 Hyderabad