Forward Deployed Engineer (AI FDE)

🚀 About Thrifty AI

We're building AI employees that can see, hear, speak, reason, and take action. Thrifty AI builds artificial humans and agentic AI systems for enterprises and government organizations. Our work spans real-time AI avatars, voice AI, LLM-powered agents, and autonomous workflows that operate across digital and physical environments. We're backed by Google for Startups, supported by India's Ministry of Electronics and Information Technology (MeitY), and part of NVIDIA Inception. We're a hands-on engineering team working to turn advances in AI into reliable systems that work in production.

📐 About the role

We’re looking for an experienced Forward Deployed Engineer (AI FDE) who can bridge the gap between advanced AI capabilities and real-world business applications. You’ll work closely with founders, product teams, engineers, and stakeholders to turn AI prototypes into reliable, production-ready solutions that solve complex business problems. This is a hands-on engineering role focused on building and deploying AI-powered applications, intelligent agents, and enterprise-grade AI workflows. You’ll own solutions end to end — from understanding business requirements and designing system architecture to integrating APIs, deploying applications, and improving performance in production. At Thrifty AI, you’ll work at the intersection of Generative AI, LLMs, agentic systems, and backend engineering. We’re looking for someone who combines strong engineering fundamentals with a problem-solving mindset, takes ownership of delivery, and can adapt quickly to evolving technical and business requirements.

🦸🏻‍♀️ What you’ll do

• Build and Deploy AI Solutions: Transform AI prototypes and proof-of-concept applications into scalable, reliable, production-ready systems.
• Engineer AI Agents and Workflows: Design, develop, and optimize LLM-powered agents, multi-step reasoning workflows, tool calling, and agent orchestration.
• Own End-to-End Delivery: Take ownership of the complete engineering lifecycle, including requirement discovery, architecture, development, testing, deployment, monitoring, and iteration.
• Integrate AI with Real-World Systems: Connect AI applications with APIs, enterprise platforms, databases, internal tools, and external services to enable practical business use cases.
• Develop RAG-Based Applications: Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including document processing, chunking, embeddings, retrieval, and context management to improve accuracy and reduce hallucinations.
• Optimize Performance and Reliability: Debug complex agent behavior, improve tool selection and reasoning flows, reduce latency, and optimize inference costs and response quality.
• Build Production Infrastructure: Implement robust backend services, error handling, retries, rate limiting, logging, monitoring, and other mechanisms required for dependable AI systems.
• Ensure Security and Scalability: Apply appropriate authentication, authorization, data protection, and deployment practices while designing systems that can scale with usage.
• Work Directly with Stakeholders: Understand customer and business requirements, translate them into technical solutions, and iterate based on feedback and real-world performance.
• Drive Continuous Improvement: Evaluate emerging AI models, frameworks, and engineering approaches to identify opportunities to improve product capabilities and delivery speed.

⭐️ What We’re Looking For

• Strong Engineering Fundamentals: Proficiency in Python, backend development, API integrations, and building reliable, scalable applications.
• Hands-on GenAI Experience: Practical experience working with LLMs, Generative AI, prompt engineering, and integrating AI capabilities into real-world applications.
• AI Agent Development: Understanding of agentic workflows, tool calling, multi-step reasoning, and frameworks such as LangGraph, LangChain, or CrewAI.
• Production-Ready Solutions: Ability to take AI prototypes beyond experimentation and build, deploy, and maintain reliable production systems.
• RAG and Knowledge Integration: Experience with RAG pipelines, embeddings, vector databases, semantic search, and improving retrieval accuracy.
• System Integration and Debugging: Ability to connect AI systems with APIs, databases, and external tools while troubleshooting complex technical issues.
• Performance and Reliability: Understanding of latency optimization, error handling, monitoring, scalability, and AI application cost optimization.
• Ownership and Problem-Solving: Ability to independently handle technical challenges, make engineering decisions, and drive solutions from concept to deployment.
• Collaboration and Adaptability: Comfortable working directly with founders, product teams, and stakeholders in a fast-paced startup environment.

The Experience at Thrifty AI

• High Ownership: Take responsibility for meaningful engineering problems and drive solutions from concept to production.
• Real-World AI Engineering: Work on practical AI applications, intelligent agents, and systems designed to solve business challenges.
• Direct Collaboration: Work closely with founders and cross-functional teams, contributing to technical decisions and product direction.
• Fast-Paced Execution: Build, test, learn, and iterate quickly without unnecessary layers of bureaucracy.
• Room to Experiment: Explore emerging AI technologies, frameworks, and architectures and translate promising ideas into useful products.
• Meaningful Impact: See how your engineering decisions influence product quality, customer outcomes, and business growth.
• Continuous Growth: Develop deeper expertise across AI engineering, system design, deployment, and production problem-solving.