AI Developer / Forward Deployed Engineer

bitsIO Inc.; India; Hybrid; INR 3,500,000 - 5,500,000; Full time

Job summary

bitsIO Inc. seeks a Forward Deployed Engineer in India to bridge core AI infrastructure with US operations. You will design and deploy custom AI agents, build complex RAG workflows, and lead live demonstrations for US customers.

Hybrid role requiring deep Python skills and enterprise-grade AI experience. You will work on agent development for health care and fintech domains, scale production-grade solutions, and collaborate across borders with US teams to optimize performance and latency.

Qualifications

• Advanced Python programming
• Extensive experience with Large Language Models (Claude preferred)
• Proven RAG system design and implementation
• Experience with agent frameworks and orchestration tools
• Strong client-facing communication skills
• Experience deploying AI on cloud platforms (AWS/GCP/Azure)

Responsibilities

• Design, build, and deploy custom AI agents for enterprise use
• Develop complex Retrieval-Augmented Generation pipelines
• Lead live technical demos for US clients
• Scale agents from PoC to production with performance monitoring
• Collaborate with US teams to align field learnings
• Ensure secure data handling and compliance during deployments

Skills

Python Proficiency

LLM & Claude

RAG Systems

LangChain / LlamaIndex

Client Communication

Cloud Deployment

Job description

Shift: US Overlap (Available until mid-day CST)

Department: AI & Forward Deployment

About bitsiO & The Role

At bitsIO, we are accelerating the adoption of enterprise AI. We don't just build theoretical

models; we deploy production-ready AI ecosystems that solve complex, real-world

operational challenges for our US-based clients.

We are looking for a highly capable Forward Deployed Engineer (FDE) based in India to

serve as the technical bridge between our core AI infrastructure and our US operations. In

this role, you will act as a hybrid software engineer, AI architect, and client-facing technical

lead. You will build custom AI Agents, design complex RAG workflows, scale these solutions

for enterprise use, and lead live technical demos for our US customers. You will be building domain specific agents for Health care and Fintech etc.

Working Hours Requirement: Because this role heavily supports US operations and

involves live customer demos, you must be available for overlapping hours until at least

mid-day (12:00 PM) US Central Standard Time (CST).

Key Responsibilities

Custom Agent Development: Design, build, and deploy custom, multi-step AI agents

using Anthropic’s Claude, tailored specifically to US client workflows and operational

bottlenecks.

RAG Pipeline Architecture: Build and optimize complex Retrieval-Augmented

to AI models ensuring high accuracy, low hallucination, and secure data handling.

Live Client Demos & Prototyping: Partner with our US operations and sales teams to

deliver compelling, highly technical product demonstrations. Translate ambiguous

client requirements into rapid AI prototypes.

Scaling & Productionization: Take AI agents from the proof-of-concept phase into

highly scalable, production-ready applications. Monitor agent performance, manage API

rate limits, and optimize latency.

Cross-Border Collaboration: Work asynchronously and synchronously with the US

core engineering and product teams to push field learnings and common client requests

Required Skills & Experience

Advanced Python Proficiency: Deep, hands-on experience writing clean, scalable, and

production-ready Python code.

AI & LLM Mastery: Extensive experience working with Large Language Models,

particularly Anthropic's Claude. Strong understanding of prompt engineering, function

calling/tool use, and context window management.

RAG Expertise: Proven ability to build sophisticated RAG systems. Familiarity with

strategies, and hybrid search.

Agentic Frameworks: Hands-on experience building autonomous or semi-autonomous

AI agents (experience with LangChain, LlamaIndex, AutoGen, CrewAI, or raw API

orchestration).

Client-Facing Communication: Exceptional verbal and written English skills. Ability to

explain complex AI concepts to non-technical stakeholders and confidently run live

Cloud & Scaling: Familiarity with deploying AI applications on cloud infrastructure

(AWS/GCP/Azure) and handling the unique challenges of scaling generative AI (caching,