Principal AI Engineer

Blitzy; Cambridge (MA); On-site; USD 100,000 - 160,000; Full time

Job summary

An innovative start-up is seeking a talented AI Engineer to join their founding team. This role offers the chance to work directly with leaders in the field, developing advanced systems that will revolutionize software creation. You'll leverage your expertise in the LangChain ecosystem to build autonomous software platforms, tackling novel challenges in LLM orchestration. The environment is fast-paced and dynamic, perfect for those who thrive on innovation and problem-solving. Join a passionate team dedicated to pushing the boundaries of technology and shaping the future of software development.

Benefits

Competitive Salary and Equity

Comprehensive health, dental, and vision insurance

401(k) with company match

Professional development budget

Opportunity to shape the future of software development

Work directly with exceptional technical leaders

Modern office in Cambridge's innovation hub

Potential for publication and conference presentations

Qualifications

• Expert-level proficiency in Python and LangChain ecosystem.
• Extensive experience with agent frameworks and LLM optimization.

Responsibilities

• Design and implement agentic systems using the LangChain ecosystem.
• Develop LLM orchestration systems for performance and cost optimization.

Skills

Python

LangChain

LLM prompt engineering

ReAct

tool use

function calling

RAG

vector databases

cloud platforms (GCP)

software engineering fundamentals

Education

Bachelor's in Computer Science or related field

Master's in AI or related field

Tools

LangGraph

LangSmith

Job description

Blitzy is a Boston, MA based Generative AI Start-up on a mission to automate custom software creation and unlock the next industrial revolution. Founded by serial entrepreneurs and AI innovators, we're backed by multiple tier 1 investors and hold dozens of Generative AI patents.

We're creating an autonomous custom software platform that will fundamentally transform how enterprise software is developed, deployed, and maintained at scale.

About the role

We are looking for an exceptional AI Engineer to join our founding team. You will work directly with our CTO and core engineering team on developing the advanced LLM and agent systems at the heart of our platform. You will leverage your deep expertise in the LangChain ecosystem and agentic development to build systems that autonomously generate high-quality enterprise software from requirements. This role offers significant influence over our technical direction and the opportunity to solve novel challenges in LLM orchestration and agentic frameworks. If your colleagues describe you as passionate, innovative, and results-driven, you are a culture fit.

What Success Looks Like

• You design and implement sophisticated agentic systems using the LangChain ecosystem that power our autonomous software development platform
• You leverage your expertise with ReAct, structured outputs, tool use, and function calling to build robust agent architectures
• You create LLM orchestration systems that maximize performance while optimizing costs
• You develop evaluation frameworks to ensure consistent, high-quality outputs from our AI systems
• You optimize our systems for production-grade reliability, scalability, and performance
• You stay at the cutting edge of LLM and agent technology, bringing new approaches into our systems
• You communicate complex technical concepts clearly to technical and non-technical stakeholders
• You take ownership of critical components and drive them from concept to completion
• You collaborate effectively with the engineering team to integrate your systems into the broader platform
• You maintain a relentless focus on quality and user outcomes
• You help establish best practices for LLM engineering within the company

Areas of Ownership

Our hiring process is designed for you to demonstrate deep expertise in LLM and agentic development.

Required Technical Experience:

• Expert-level proficiency in Python and the LangChain ecosystem (LangChain, LangGraph, LangSmith)
• Extensive experience implementing agent frameworks and concepts including ReAct, structured outputs, tool use, and function calling
• Deep understanding of large language models (architectures, capabilities, limitations)
• Strong experience with LLM prompt engineering and optimization techniques
• Proficiency with retrieval-augmented generation (RAG) and vector databases
• Experience with cloud platforms (GCP preferred) for deploying and scaling LLM applications
• Strong software engineering fundamentals with a focus on building robust, maintainable systems
• Knowledge of LLM evaluation approaches and metrics

Ways to stand out

• Experience fine-tuning LLMs for specialized use cases
• Contributions to open-source LLM or agent projects
• Experience building multi-agent systems that solve complex problems
• Prior experience building AI-driven developer tools or code-generation systems
• Knowledge of efficient inference techniques and cost optimization for LLMs
• Background in software development tools or developer productivity

You'll Get...

• Competitive Salary and Equity
• Comprehensive health, dental, and vision insurance
• 401(k) with company match
• Professional development budget
• The opportunity to shape the future of software development
• Work directly with and learn from exceptional technical leaders
• Modern office in Cambridge's innovation hub
• Potential for publication and conference presentations (when aligned with business strategy)

Culture

Who we are: Our Co-Founder and CTO is a Serial Gen AI Inventor who grew up in Pune, India, is a BITS Pilani graduate, and worked at NVIDIA's Pune office for 6 years. There, he was promoted 5 times in 6 years and was transferred to the NVIDIA Headquarters in Santa Clara, California. After making significant contributions to NVIDIA, he proceeded to attend Harvard for his dual Masters in Engineering and MBA from HBS. Our other Co-Founder/CEO is a successful Serial Entrepreneur who has built multiple companies. As a team, we work very hard, have a curious mind-set, and believe in a low-ego high output approach.

We move Blitzy Fast. Time is both our company's and our clients' most precious asset. We move quickly and decisively to innovate internally and deliver exceptional software externally.

We have a Championship Mindset. We operate like a professional sports team. We win as a team by holding ourselves and each other to high standards, collaborating in-person, and remaining focused on the mission.

What we ask of you:

Please ask yourself if you are ready for a challenge before applying. Even in optimal conditions, Start-Ups are hard, and are always a lot of work. What you do week to week will change. If this feels exciting, not concerning, that's a good sign.

This role requires exceptional talent and dedication. You'll be solving novel problems and helping define the future of autonomous software development. This means you'll need to be comfortable with ambiguity, adaptable to evolving priorities, and ready to push technical boundaries.

To apply

Apply through this posting with your resume and a brief note about why you're interested in revolutionizing software development through AI.

Process

Here's what you can expect:

1. Initial application review
2. Technical discussion with an engineering leader
3. On-site interviews with the founding team
4. Final conversation with the CTO
5. Offer and onboarding discussion

Blitzy is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.