Viewing profile — jared_stewart
jared_stewart
HN member- Joined
- Thu, Feb 04, 2021, 3:18 AM UTC
- HN karma
- 29
- Public activity
- 14 items
- HN profile
- View on Hacker News ↗
About jared_stewart
Recent highlights: - Helped scale Proofpoint's Email Fraud Defense from ~$30M to $200M+ ARR (staff eng, 4.5 years) - Led AI/ML team at Velocity Global automating contract parsing - eliminated thousands of manual hours using LLMs - Director of Data Engineering at CoBank - reduced AWS costs 25%, built enterprise APIs
Wanted to design buildings as a kid, ended up architecting systems instead. Started in civil engineering, worked on HD Maps at Mercedes-Benz R&D and Threat Research at Level 3. Turns out I just like making things that don't fall over - whether that's bridges or data pipelines.
What drives me: Making complex systems both powerful and usable. I love the early stages where you're figuring out what to build, not just how.
Looking for: Senior IC or leadership roles shaping data/AI strategy. Open to fintech, security, infrastructure - anywhere with interesting challenges and smart people.
PhD from Colorado School of Mines. Always happy to chat and make new connections Connect: jared.andrew.stewartgmail.com | jaredstewart.io
Recent public activity
-
comment
Comment #46991419
The server exposes a straightforward API so wrapping it in MCP should be straight forward. The agent / skill interacts with the server using the cli implementation (part of the ski…
-
comment
Comment #46991362
Typed languages definitely provide richer signal in there signatures - and my experience has been that I get more reliable generations from those languages. On the efficiency point…
-
comment
Comment #46991237
I see, so the context adapts as the LLM interacts with the codebase across requests? That's a clever implicit flow for ranking. The difference in my approach is that exploration is…
-
comment
Comment #46984809
will take a look at opencode, thanks for sharing!
-
comment
Comment #46984801
Aider's repo-map concept is great! thanks for sharing, I'd not been aware of it. Using tree-sitter to give the LLM structural awareness is the right foundation IMO. The key differe…
-
comment
Comment #46984410
I've been tinkering with it substantially and the most I can say is that it generally doesn't trigger automatically :( Claude has a really, really strong affinity for it's existing…
-
comment
Comment #46984232
I don't see why it wouldn't - but I'm not familiar with setup / integration on other platforms. Would love to hear more about your stack and see if we can't find a way for you to t…
-
comment
Comment #46984213
Tree-sitter and LSP solve different problems. LSP is a full fledged semantics solution providing go-to-definition functionality, trace references, type info etc. But requires a ful…
-
comment
Comment #46984077
anecdotally, it seems like this helps find better places for code to sit, understands the nuances of a code base better, and does a better job avoiding duplicate functionality. it'…
-
story
Show HN: CodeRLM – Tree-sitter-backed code indexing for LLM agents
I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories…
-
comment
Comment #45564714
I've been working to build some tools for detecting and monitoring lookalike domains - the kinds of things used in phishing / brand impersonation attacks. My current prototype scan…
-
comment
Comment #45442261
Location: Denver, CO Remote: yes Role: Staff+ Engineer, Tech Lead, Engineering Manager, or Co-founder I'm a serial builder who thrives in the space between engineering and business…
-
comment
Comment #45093242
Location: Denver, CO Remote: yes Role: Staff+ Engineer, Tech Lead, Engineering Manager, or Co-founder I'm a serial builder who thrives in the space between engineering and business…
- comment