Applied AI Research Engineer - Model Cost Optimization
About Blitzy
Blitzy is a Cambridge, MA based AI software development platform on a mission to revolutionize the software development life cycle by autonomously building custom software to unlock the next industrial revolution. We're transforming how enterprises build software, turning enterprise requirements into production-ready code with an agentic software development platform that can autonomously execute 80% of the quantum of software development work. We're backed by multiple tier 1 investors, and have proven success as founders of previous start-ups.
Location: Cambridge, MA (in-office)
Compensation: $210,000 - $260,000 base salary (bonus + equity commensurate with experience)
The Role
Blitzy's agentic platform routes enormous volumes of work across many different models, and the model landscape shifts constantly, with new releases changing the price-performance tradeoff on a near-weekly basis. We're looking for an Applied AI Researcher to join as an early member of our applied AI research team, dedicated to model cost optimization: choosing the right model for the right task at the right time. You'll build the research, evaluation, and routing logic that lets Blitzy's platform dynamically select the most cost-effective model for every step of the software development lifecycle, without sacrificing output quality.
What Success Looks Like
Blitzy's platform reliably selects the most cost-efficient model for each task without any measurable drop in code quality or task success rate.
You've built a repeatable framework for benchmarking new models against Blitzy's real workloads within days of their release.
Model spend per unit of delivered work trends steadily downward, even as usage scales.
Engineering and research teams treat your evaluation and routing infrastructure as the source of truth for model selection decisions.
Areas of Ownership
Design and maintain evaluation pipelines that benchmark models across cost, latency, and quality for Blitzy's core software development workflows.
Build and iterate on dynamic model-routing logic that selects the optimal model for a given task in real time.
Continuously track the model landscape and rapidly integrate and evaluate new model releases as they ship.
Partner with the platform engineering team to productionize routing and optimization logic at scale.
Define and track the metrics that quantify the cost-to-quality tradeoff across the platform.
Required Experience
Strong experience in applied machine learning or AI research, ideally with hands-on work evaluating or fine-tuning large language models.
Solid software engineering skills with the ability to ship production-quality code, not just research prototypes.
Familiarity with LLM evaluation methodologies and benchmarking frameworks.
Comfort working with the economics of model inference, including cost, latency, and throughput tradeoffs.
A strong bias toward experimentation and rapid iteration.
What Makes You Stand Out
A PhD or equivalent degree in AI Systems or Applied AI Research from a reputable university.
Prior experience building model routing, model selection, or model-cascading systems in production.
A track record of publications, open-source contributions, or projects related to LLM evaluation or optimization.
Experience working directly with foundation model providers or API ecosystems across multiple vendors.
A founder's mentality: comfort with ambiguity and a drive to build from zero as an early team member.
What Makes This Role Different
This is a ground-floor opportunity to shape how Blitzy's applied AI research team approaches model strategy from day one. As an early member of the team, you'll have outsized influence over the research direction, tooling, and infrastructure that the rest of the company will build on, with direct visibility into how your work affects both the cost structure and the capabilities of Blitzy's platform.
Our Culture
Who we are:
Led by two pioneering co-founders we are one of the fastest growing companies in the U.S., creating our own category of enterprise autonomous software development. We automate thousands of hours of software development for our customers, which includes strong representation within the Fortune 500.
How we work:
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.
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.
Passion for Invention: We're pushing the frontier of what's possible, requiring constant innovation and iteration.
We Work for the Customer: We focus on delivering outsized value to the customers we work with and expanding those relationships into deep, meaningful partnerships.
We believe in being 'everyday athletes'—taking care of ourselves so we can bring our best minds to work. We promote great sleep, movement, and restorative activities for optimal mental performance. It makes for a happier and more productive team.
Blitzy is an equal opportunity employer committed to building a diverse and inclusive team. We believe different perspectives make us stronger.