Senior AI Engineer, Agentic Evaluation & V&V

Meet Slingshot

At Slingshot Aerospace, we're on a mission to make space safer and more secure for everyone. Our work directly impacts global security, disaster response, climate monitoring, and the critical infrastructure that connects our world. We're a team of builders, thinkers, and problem-solvers who believe that the next generation of space operations will be powered by better data and smarter software.

We move fast, we're not afraid to fail, and we believe the best ideas can come from anywhere—whether you're in engineering, sales, product, or operations. If you want to work on something that truly matters, with people who care deeply about the impact we're making and help shape the future of an industry that's just getting started, you're in the right place.

What You’ll Be Launching

As a Senior AI Engineer focused on Agentic Evaluation and Verification and Validation (V&V), you will join the AI and Data Science team within Slingshot’s Research and Development organization. You will contribute to advancing how intelligent systems are evaluated and validated for mission-critical space operations.

This role focuses on building and scaling evaluation frameworks, benchmarks, and simulation-backed validation systems for agentic AI systems, including multi-step, tool-using, and autonomous decision-making workflows powered by LLMs and reinforcement learning. Your work will directly support the development of reliable and trustworthy autonomous mission planning systems.

You will partner closely with AI researchers and domain experts to translate real-world mission concepts into structured, testable evaluation systems.

Your Mission (Should you choose to accept it)

Extend and maintain Slingshot’s V&V SDK and evaluation framework for simulation-backed validation of agentic AI systems

Design and implement agent-level and end-to-end evaluations, including benchmark scenarios, scoring logic, and experiment harnesses

Build benchmark scenarios and tooling that measure planning, reasoning, and operational performance for autonomous mission planning systems

Translate astrodynamics and mission-domain concepts into executable evaluation scenarios and simulation configurations

Develop reusable SDK interfaces, adapters, and evaluation utilities that connect V&V systems, TALOS benchmarks, and agent workflows

Define and apply metrics for capability evaluation, failure analysis, regression detection, and comparative benchmarking

Partner with cross-functional teams to identify evaluation needs and contribute to improving coverage of critical capabilities

Contribute to best practices for evaluating complex, autonomous AI systems

Uphold strong engineering standards through testing, documentation, reproducibility, and maintainable system design

Pre-flight Checklist

6+ years of experience in software engineering, machine learning engineering, applied AI, or equivalent experience

Strong Python engineering skills with experience building SDKs, libraries, or evaluation tooling

Experience designing evaluation frameworks, benchmarks, metrics, or test harnesses for AI/ML systems

Ability to analyze system behavior, identify failure modes, and evaluate performance in complex autonomous or semi-autonomous systems

Familiarity with modern agent frameworks, orchestration patterns, or protocol-based integrations

Experience working in cross-functional, multidisciplinary teams

Strong written and verbal communication skills

Bachelor’s degree in a relevant science or engineering field, or equivalent experience

Must be a U.S. citizen and eligible to obtain and maintain a government security clearance

Bonus Cargo

Experience in autonomous systems such as self-driving or ADAS, including perception, planning, simulation, or safety validation

Experience developing or evaluating agentic AI systems, including multi-step, tool-using, or autonomous workflows (e.g., LLM-based agents, planning agents, or reinforcement learning approaches)

Experience with reinforcement learning systems and simulation-based evaluation

Familiarity with benchmark design, experiment tracking, and trace-based evaluation workflows

Experience with orchestration frameworks such as LangGraph or similar tools

Knowledge of astrodynamics, orbital mechanics, or spacecraft mission planning

Experience translating mission or operational concepts into measurable evaluation scenarios

Familiarity with physics-based simulation, trajectory analysis, or space-domain modeling

Experience with observability and experiment tooling such as MLflow, Opik, or similar platforms

Experience transitioning advanced research systems into production environments

We're building a constellation here, not looking for identical satellites. Every member of the team brings different capabilities to the same mission. If your orbit intersects with ours and you're mission-ready, send it.

Location: Remote, US

Salary: $150,000-$250,000

Classification: Full time Exempt (learned professional exemption)

US-based Candidates: we are currently only able to hire residents of the following U.S. states: AL, AZ, CA, CO, DC, FL, GA, HI, IL, IN, KS, MA, MD, MI, MN, MO, MT, NC, NJ, NM, NV, NY, OH, OK, OR, RI, TN, TX, UT, VA, WA, WI, WV We are unable to consider candidates residing in other U.S. states at this time.

Internationally-based Candidates: we are currently only able to hire residents of the following locations: United Kingdom. We are unable to consider candidates residing in other countries at this time.

Equity, Diversity & Inclusion are key to our success. We are an Equal Opportunity Employer and our employees are people with different strengths, experiences, and backgrounds, who share a passion for creating a safer, more connected world. Diversity not only includes race and gender identity, but also national origin, citizenship, sex, color, veteran status, disability, genetic information, or any other protected characteristic that is part of one’s identity.

All of our employees’ points of view are key to our success, and we embrace individuality.